{"id":"https://openalex.org/W4402390097","doi":"https://doi.org/10.1109/ialp63756.2024.10661176","title":"Speech de-identification data augmentation leveraging large language model","display_name":"Speech de-identification data augmentation leveraging large language model","publication_year":2024,"publication_date":"2024-08-04","ids":{"openalex":"https://openalex.org/W4402390097","doi":"https://doi.org/10.1109/ialp63756.2024.10661176"},"language":"en","primary_location":{"id":"doi:10.1109/ialp63756.2024.10661176","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ialp63756.2024.10661176","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Asian Language Processing (IALP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/conference_contribution/Speech_de-identification_data_augmentation_leveraging_large_language_model/26303368","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107100236","display_name":"Priyanshu Dhingra","orcid":null},"institutions":[{"id":"https://openalex.org/I98210582","display_name":"Rajiv Gandhi Institute of Petroleum Technology","ror":"https://ror.org/00n7swc17","country_code":"IN","type":"education","lineage":["https://openalex.org/I98210582"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Priyanshu Dhingra","raw_affiliation_strings":["Rajiv Gandhi Institute of Petroleum Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rajiv Gandhi Institute of Petroleum Technology","institution_ids":["https://openalex.org/I98210582"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087503576","display_name":"Satyam Kumar Agrawal","orcid":"https://orcid.org/0000-0001-8127-6380"},"institutions":[{"id":"https://openalex.org/I11880225","display_name":"National Institute of Technology Karnataka","ror":"https://ror.org/01hz4v948","country_code":"IN","type":"education","lineage":["https://openalex.org/I11880225"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Satyam Agrawal","raw_affiliation_strings":["National Institute of Technology Karnataka"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Technology Karnataka","institution_ids":["https://openalex.org/I11880225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075624536","display_name":"Chandra Sekar Veerappan","orcid":null},"institutions":[{"id":"https://openalex.org/I168639165","display_name":"Singapore Institute of Technology","ror":"https://ror.org/01v2c2791","country_code":"SG","type":"education","lineage":["https://openalex.org/I168639165"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chandra Sekar Veerappan","raw_affiliation_strings":["Singapore Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore Institute of Technology","institution_ids":["https://openalex.org/I168639165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048806307","display_name":"Thi Nga Ho","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Thi Nga Ho","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070872826","display_name":"Eng Siong Chng","orcid":"https://orcid.org/0000-0001-6257-7399"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Eng Siong Chng","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055221016","display_name":"Rong Tong","orcid":"https://orcid.org/0000-0003-3410-8354"},"institutions":[{"id":"https://openalex.org/I168639165","display_name":"Singapore Institute of Technology","ror":"https://ror.org/01v2c2791","country_code":"SG","type":"education","lineage":["https://openalex.org/I168639165"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Rong Tong","raw_affiliation_strings":["Singapore Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore Institute of Technology","institution_ids":["https://openalex.org/I168639165"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2219,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.8289756,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"97","last_page":"102"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9807000160217285,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9508000016212463,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8425545692443848},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5993461608886719},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5142812132835388},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5089640617370605},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.485691636800766},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.47660985589027405},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.45510756969451904},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35548073053359985},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.24070170521736145},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.16476398706436157}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8425545692443848},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5993461608886719},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5142812132835388},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5089640617370605},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.485691636800766},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.47660985589027405},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.45510756969451904},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35548073053359985},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.24070170521736145},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.16476398706436157},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ialp63756.2024.10661176","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ialp63756.2024.10661176","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Asian Language Processing (IALP)","raw_type":"proceedings-article"},{"id":"pmh:oai:figshare.com:article/26303368","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Speech_de-identification_data_augmentation_leveraging_large_language_model/26303368","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/26303368","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Speech_de-identification_data_augmentation_leveraging_large_language_model/26303368","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320311649","display_name":"Ministry of Education","ror":"https://ror.org/036nq5137"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2033357968","https://openalex.org/W2134426579","https://openalex.org/W2406932913","https://openalex.org/W2621075239","https://openalex.org/W2914417638","https://openalex.org/W2921018690","https://openalex.org/W2963956191","https://openalex.org/W2973072704","https://openalex.org/W3095918555","https://openalex.org/W4221139374","https://openalex.org/W4225585117","https://openalex.org/W4297841645","https://openalex.org/W4385569624","https://openalex.org/W4385572421","https://openalex.org/W4388291822","https://openalex.org/W4396759394","https://openalex.org/W6810404315"],"related_works":["https://openalex.org/W2924380321","https://openalex.org/W1998541766","https://openalex.org/W2064542902","https://openalex.org/W2262900283","https://openalex.org/W1985349217","https://openalex.org/W2098508228","https://openalex.org/W2532974797","https://openalex.org/W2624072012","https://openalex.org/W1508853749","https://openalex.org/W69308499"],"abstract_inverted_index":{"This":[0,50],"work":[1],"addresses":[2],"the":[3,13,88,110],"challenge":[4],"of":[5,15,90],"limited":[6],"real-world":[7],"speech":[8,11,23,60],"data":[9,38,47,63,71,92],"in":[10,95],"de-identification,":[12],"process":[14,75],"removing":[16],"Personally":[17],"Identifiable":[18],"Information":[19],"(PII).":[20],"We":[21],"formulate":[22],"de-identification":[24],"as":[25],"a":[26,46,53,77],"named":[27],"entity":[28],"recognition":[29],"(NER)":[30],"task":[31],"specifically":[32],"for":[33,81],"spoken":[34,101],"English.":[35],"To":[36],"overcome":[37],"scarcity":[39],"and":[40],"enhance":[41],"NER":[42,79,98],"performance,":[43],"we":[44,116],"propose":[45],"augmentation":[48,93],"approach.":[49],"approach":[51],"leverages":[52],"large":[54],"language":[55,102],"model":[56,80],"to":[57,105],"generate":[58],"synthetic":[59],"style":[61],"text":[62],"enriched":[64],"with":[65],"diverse":[66],"PII":[67,83],"entities.":[68],"The":[69],"generated":[70],"undergoes":[72],"an":[73],"iterative":[74],"using":[76,120],"customized":[78],"semi-automatic":[82],"annotation.":[84],"Our":[85],"analysis":[86,119],"demonstrates":[87],"effectiveness":[89],"this":[91],"strategy":[94],"significantly":[96],"improving":[97],"performance":[99,118],"on":[100],"text.":[103],"Furthermore,":[104],"gain":[106],"deeper":[107],"insights":[108],"into":[109],"specific":[111],"errors":[112],"made":[113],"during":[114],"NER,":[115],"employ":[117],"alternative":[121],"evaluation":[122],"metrics.":[123]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}